Rate of convergence and Edgeworth-type expansion in the entropic central limit theorem

Abstract

An Edgeworth-type expansion is established for the entropy distance to the class of normal distributions of sums of i.i.d. random variables or vectors, satisfying minimal moment conditions.

Published in at http://dx.doi.org/10.1214/12-AOP780 the Annals of Probability (http://www.imstat.org/aop/) by the Institute of Mathematical Statistics (http://www.imstat.org)

Cited by in corpus (23)

• On Kac's Chaos And Related Problems
• Entropy bounds on abelian groups and the Ruzsa divergence
• Full counting statistics and the Edgeworth series for matrix product states
• Statistical Inference for the Population Landscape via Moment Adjusted Stochastic Gradients
• A stroll along the gamma
• Slicing ${\ell }_p$-balls reloaded: stability, planar sections in ${\ell }_1$
• Two remarks on generalized entropy power inequalities
• Links between the Logarithmic Sobolev Inequality and the convolution inequalities for Entropy and Fisher Information
• A de Bruijn identity for symmetric stable laws
• Rényi divergence and the central limit theorem
• An invariance principle under the total variation distance
• Superconvergence phenomenon in Wiener chaoses
• Entropy Jumps for Radially Symmetric Random Vectors
• Richter's local limit theorem,its refinement,and related results
• Fisher information and the central limit theorem
• Existence of Stein Kernels under a Spectral Gap, and Discrepancy Bound
• Berry-Esseen bounds in the entropic central limit theorem
• Entropy and thinning of discrete random variables
• Stein's method, logarithmic Sobolev and transport inequalities
• Convergence to Stable Laws in Relative Entropy
• A Multi-Dimensional Central Limit Bound and its Application to the Euler Approximation of Lévy SDEs
• Maximal correlation and the rate of Fisher information convergence in the Central Limit Theorem
• Edgeworth-type expansion in the entropic free CLT